CN118262302B - Binocular identification-based 5G intelligent road management method and system - Google Patents
Binocular identification-based 5G intelligent road management method and system Download PDFInfo
- Publication number
- CN118262302B CN118262302B CN202410679084.XA CN202410679084A CN118262302B CN 118262302 B CN118262302 B CN 118262302B CN 202410679084 A CN202410679084 A CN 202410679084A CN 118262302 B CN118262302 B CN 118262302B
- Authority
- CN
- China
- Prior art keywords
- traffic
- vehicle
- road
- lane
- binocular
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 58
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 65
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000004891 communication Methods 0.000 claims abstract description 18
- 230000006399 behavior Effects 0.000 claims description 59
- 238000004088 simulation Methods 0.000 claims description 30
- 230000008859 change Effects 0.000 claims description 23
- 230000004888 barrier function Effects 0.000 claims description 22
- 230000006978 adaptation Effects 0.000 claims description 13
- 238000002372 labelling Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 13
- 241000251468 Actinopterygii Species 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 7
- 230000001965 increasing effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000011217 control strategy Methods 0.000 description 3
- 230000010485 coping Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a 5G intelligent road traffic management method and system based on binocular identification, and relates to the technical field of intelligent traffic, wherein the method comprises the following steps: a binocular recognition camera is deployed on a road brake control road section, and vehicle image data in the road brake control road section are captured in real time; constructing a gate traffic analysis model, identifying vehicle image data, and analyzing an identification result by using a cluster tracking algorithm to obtain traffic flow state characteristics; judging the current road gate traffic mode according to the traffic flow state characteristics; and sending the judging result to an intelligent road brake management platform by using a 5G communication network, and remotely controlling the road brake release vehicle based on the current road brake traffic mode. According to the invention, vehicle information is captured in real time through a binocular identification technology, the traffic flow state characteristics are accurately analyzed by combining a cluster tracking algorithm, the traffic flow state can be intelligently judged, the opening and closing of the road gate can be adjusted according to the real-time traffic condition, and vehicles are guided to reasonably split and merge.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a 5G intelligent road traffic management method and system based on binocular identification.
Background
Intelligent Traffic Systems (ITS) are an important component of modern traffic management, and implement collection, processing and application of traffic information by using technologies such as computers, electronic communication and control, so as to optimize traffic management and services. With the development of technology, intelligent traffic technology has been widely applied to aspects of traffic flow monitoring, vehicle navigation, traffic signal control, etc., however, although the prior art significantly improves traffic efficiency and safety, there are some disadvantages: for example, conventional traffic monitoring systems rely mainly on ground induction coils, video monitoring, etc. devices, which are limited in accuracy and real-time in information collection; at the same time, most existing systems rely on centralized data processing and control modes, which can lead to delays in data processing and decision making, especially during peak hours or emergency situations; therefore, although the existing intelligent traffic technology improves traffic management to a great extent, there is still room for improvement in terms of data processing efficiency, real-time performance and accuracy.
In intelligent traffic systems, traffic management is an important loop, which is directly related to the control and management of traffic flow. Conventional road traffic management techniques typically control road gate opening and closing based on a fixed schedule or simple traffic flow calculation, lack dynamic response capability to complex traffic conditions, and often cannot effectively cope with sudden congestion during peak traffic periods or cannot effectively save energy and reduce operating costs during periods of low traffic flow; in addition, due to the lack of high-precision vehicle recognition and tracking capabilities, conventional road management techniques are not well behaved in terms of vehicle classification, accurate calculation of traffic smoothness, etc., which limits their effectiveness in traffic control and accident prevention.
The main defects of the existing barrier gate technology are that the data collection capability and the processing efficiency are insufficient, firstly, the existing barrier gate technology depends on traditional sensing and monitoring equipment, and the data collection accuracy and the comprehensiveness of the equipment in a complex environment are limited; second, traditional data processing methods are typically centralized, which may lead to processing delays during peak hours that do not respond in real-time to bursty traffic conditions; in addition, the prior art has limited capability in traffic pattern analysis and prediction, and effective traffic flow control under complex conditions is difficult to realize; finally, the existing barrier gate technology has limited intelligent degree, and most decisions still need manual intervention, which not only increases the operation cost, but also limits the flexibility and efficiency of traffic management; therefore, a barrier gate technology capable of realizing high automation and intelligent management is needed, and obvious defects of the prior art in the aspects of adapting to complex traffic environment and improving traffic safety and efficiency are overcome.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a 5G intelligent road traffic management method and system based on binocular identification, which have the advantages of improving traffic efficiency, enhancing safety guarantee and promoting integral optimization of an intelligent traffic system, thereby solving the problems that the prior art has obvious defects in adapting to complex traffic environment and improving traffic safety and efficiency.
For this purpose, the invention adopts the following specific technical scheme:
according to one aspect of the present invention, there is provided a binocular recognition-based 5G intelligent road management method, the binocular recognition-based 5G intelligent road management method comprising the steps of:
S1, deploying binocular identification cameras on a road brake control road section, and capturing vehicle image data in the road brake control road section in real time;
S2, constructing a gate traffic analysis model, identifying vehicle image data, and analyzing an identification result by using a cluster tracking algorithm to obtain traffic flow state characteristics;
s3, judging the current road gate traffic mode according to the traffic flow state characteristics;
And S4, sending the judging result to the intelligent gateway management platform by using the 5G communication network, and remotely controlling the gateway release vehicle based on the current gateway traffic mode.
Further, deploying a binocular identification camera on a road brake control road section, capturing vehicle image data in the road brake control road section in real time comprises the following steps:
S11, deploying binocular identification cameras on a road brake control road section, initializing binocular identification camera parameters and calibrating synchronously;
S12, capturing continuous video frames of the vehicles in the control road section in real time by using the calibrated binocular identification cameras and preprocessing the video frames;
And S13, generating a depth map based on the preprocessed video frame to obtain vehicle image data.
Further, constructing a gate traffic analysis model, identifying vehicle image data, and analyzing the identification result by using a cluster tracking algorithm to obtain traffic flow state characteristics, wherein the method comprises the following steps:
S21, constructing a gate traffic analysis model, and identifying vehicle characteristics in vehicle image data;
s22, completing classification and labeling of the vehicles according to the identification result;
s23, analyzing traffic flow state characteristics of the road brake control road section by using a cluster tracking algorithm based on the classification and labeling results.
Further, based on the classification and labeling results, analyzing traffic flow state characteristics of the road traffic control road section by using a cluster tracking algorithm comprises the following steps:
s231, selecting an evaluation index based on the classification and labeling results, and normalizing the data of different evaluation indexes;
S232, simulating the movement of the road traffic control road section vehicles in the traffic network by using a cluster tracking algorithm;
S233, according to the simulation result, the traffic fluency of each lane is calculated respectively, and the traffic state characteristics of the road brake control section are obtained.
Further, simulating movement of a vehicle in a traffic network on a road segment controlled by a road thyristor by using a cluster tracking algorithm comprises the following steps:
s2321, initializing a simulated vehicle position by using a cluster tracking algorithm and setting a movement rule;
S2322, simulating lane-changing and lane-splitting behaviors of the vehicle based on the split movement rule;
s2323, simulating the same-road converging behavior of the vehicle based on the converging movement rule.
Further, based on the split movement rule, simulating the lane-changing split behavior of the vehicle comprises the following steps:
s23221, analyzing the current traffic condition, and providing an optional path for the simulated vehicle;
s23222, evaluating the influence of lane change and diversion behaviors on traffic flow based on the selectable path, and determining a safe path;
s23223, executing lane change operation according to the safety path to complete the lane change and diversion behavior of the simulated vehicle;
Based on the confluence movement rule, the simulation of the same-lane confluence behavior of the vehicle comprises the following steps:
S23231, collecting driving data of vehicles in the same lane, and evaluating interaction among the vehicles;
s23232, analyzing how the vehicle responds to the behaviors of other vehicles, and setting a speed and a distance threshold value in the converging lane;
s23233, simulating vehicle running according to the set threshold value, and completing simulating the same-road converging behavior of the vehicle.
Further, according to the simulation result, the traffic fluency of each lane is calculated respectively, and the traffic flow state characteristics of the road controlled by the traffic gate are obtained, which comprises the following steps:
S2331, calculating regional traffic fluency by using a granularity regional characteristic algorithm according to the simulation result of the lane change and diversion behavior of the vehicle;
S2332, calculating global traffic fluency by using a granularity global adaptation algorithm according to the simulation result of the same-lane converging behavior of the vehicle;
s2333, comparing the regional traffic fluency with the global traffic fluency, and updating the simulated vehicle position based on the comparison result;
S2334, repeating the steps S2331-S2333 until the preset iteration times are reached;
and S2335, collecting the final position of the simulated vehicle to obtain the traffic flow state characteristics of the road brake control road section.
Further, according to the simulation result of the lane change and diversion behavior of the vehicle, calculating the regional traffic fluency by using the granularity regional characteristic algorithm comprises the following steps:
S23311, selecting a vehicle neighborhood direction and extracting a vehicle neighborhood direction vector characteristic according to a vehicle lane change and diversion behavior simulation result;
s23312, marking each vehicle neighborhood based on the extracted neighborhood direction vector features;
s23313, calculating a vehicle neighborhood mean value by using a granularity region characteristic algorithm according to each vehicle neighborhood to obtain region passing fluency.
Further, according to the simulation result of the co-channel converging behavior of the vehicle, calculating the global traffic fluency by using the granularity global adaptation algorithm comprises the following steps:
s23321, initializing a vehicle flow cluster according to the simulation result of the same-road confluence behavior of the vehicles, and evaluating the fitness of each vehicle;
S23322, calculating the speed and the position of the vehicles in the vehicle flow cluster by using a granularity global adaptation algorithm based on the evaluation result;
And S23323, updating the speed and the position of the vehicle according to the calculation result to obtain the global traffic fluency.
According to another aspect of the present invention, there is also provided a 5G intelligent road management system based on binocular identification, the 5G intelligent road management system based on binocular identification including:
The deployment acquisition module is used for deploying binocular identification cameras on the road brake control road section and capturing vehicle image data in the road brake control road section in real time;
the recognition analysis module is used for constructing a gate traffic analysis model, recognizing vehicle image data, and analyzing the recognition result by utilizing a cluster tracking algorithm to obtain traffic flow state characteristics;
The mode judging module is used for judging the current road gate traffic mode according to the traffic flow state characteristics;
The communication management module is used for sending the judging result to the intelligent barrier management platform by utilizing the 5G communication network and remotely controlling the barrier release vehicle based on the current barrier traffic mode;
the deployment acquisition module is connected with the mode judgment module through the recognition analysis module, and the mode judgment module is connected with the communication management module.
The beneficial effects of the invention are as follows:
(1) The traffic efficiency and the fluidity are improved: according to the invention, vehicle information is captured in real time through a high-precision binocular identification technology, and the traffic flow state characteristics are accurately analyzed by combining a cluster tracking algorithm, so that accurate data support is provided for road traffic management; meanwhile, the traffic flow state is judged intelligently, and the opening and closing of the road gate are adjusted according to the real-time traffic condition, so that vehicles are guided to split and merge reasonably: in the traffic peak period, the traffic pressure can be effectively relieved and the congestion can be reduced by increasing the traffic capacity of a specific gate lane or adjusting signal lamps; in a period of low traffic flow, energy consumption can be reduced by reducing unnecessary barrier gate operation, and an energy-saving effect is realized.
(2) The traffic safety and accident handling capability are enhanced: according to the invention, by arranging the binocular identification cameras, the vehicle condition in the road brake control road section can be captured in real time, and a basis is provided for illegal driving behaviors or potential accidents; meanwhile, by utilizing the rapid response characteristic of the 5G communication network, when potential safety hazards are detected, the intelligent road brake management platform can rapidly adjust traffic modes or implement emergency measures, such as closing road brakes and adjusting signal lamps, so as to prevent accidents, and the response mechanism can remarkably reduce response time when handling traffic accidents and emergency situations, and effectively protect the safety of drivers and passengers.
(3) Facilitating overall optimization of the intelligent transportation system: the traffic behavior of the vehicle is further analyzed deeply through the gate traffic analysis model and the cluster tracking algorithm, flow and behavior data of a plurality of gate nodes are provided for the urban traffic system, and the urban traffic command center is helped to better understand and predict the traffic flow mode, so that a more scientific decision is made; in addition, the 5G communication technology ensures high-efficiency information exchange and cooperative work between each traffic node and facilities, and through data sharing and linkage control, the efficiency of a plurality of gateway nodes is improved, and data support is provided for promoting the intellectualization of the whole urban traffic system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow diagram of a 5G intelligent road management method based on binocular identification according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a 5G intelligent road thyristor management system based on binocular recognition according to an embodiment of the present invention.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
According to the embodiment of the invention, a 5G intelligent gateway management method and system based on binocular identification are provided.
The invention will be further described with reference to the accompanying drawings and the specific embodiments, as shown in fig. 1, according to an embodiment of the invention, there is provided a 5G intelligent road management method based on binocular identification, the 5G intelligent road management method based on binocular identification including the following steps:
S1, deploying binocular identification cameras on a road brake control road section, and capturing vehicle image data in the road brake control road section in real time;
S2, constructing a gate traffic analysis model, identifying vehicle image data, and analyzing an identification result by using a cluster tracking algorithm to obtain traffic flow state characteristics;
s3, judging the current road gate traffic mode according to the traffic flow state characteristics;
Specifically, collecting the traffic flow state characteristics obtained in the previous step, and performing intelligent decision based on the traffic flow characteristics and historical data to judge the corresponding road gate traffic mode, including: the traffic control method comprises the following steps of (1) a normal mode, a peak period mode and a low flow mode, wherein the opening frequency and the duration of a barrier gate in each mode are different, in the traffic peak period, the peak period mode is selected, the opening frequency of part of the barrier gate is increased or the opening time is prolonged, the timing of signal lamps at an intersection is optimized, real-time traffic information is provided by using a roadside information board, vehicles are guided to select less-congested routes so as to better coordinate traffic flow, waiting time is reduced, and vehicle passing efficiency is improved; when the traffic flow is normal, selecting to maintain a normal mode, keeping the standard opening frequency and duration of the barrier gate, and monitoring the traffic condition in real time through binocular identification equipment so as to rapidly cope with emergency; in the period of low traffic flow, a low flow mode is selected, the opening frequency of part of the road gates is reduced, the operation mode of the signal lamp is adjusted, invalid circulation is reduced, energy consumption is reduced, and an energy-saving effect is achieved.
And S4, sending the judging result to the intelligent gateway management platform by using the 5G communication network, and remotely controlling the gateway release vehicle based on the current gateway traffic mode.
Specifically, the judging result of the traffic mode of the barrier gate is rapidly sent to the intelligent barrier gate management platform through the 5G network, the intelligent barrier gate management platform comprises related data and instructions of a peak time mode, a normal mode and a low flow mode, after the management platform receives the data, the control platform remotely controls the opening and closing of the barrier gate based on the current traffic mode of the barrier gate, the control strategy comprises the control strategy of adjusting the opening frequency, the duration and the specific lane of the barrier gate, and meanwhile, the operation condition of the barrier gate and the real-time change of peripheral traffic flow can be continuously tracked through the real-time monitoring function of the management platform, and the control strategy of the barrier gate can be adjusted in real time to cope with emergency situations if necessary.
In one embodiment, deploying a binocular recognition camera at a road traffic control segment, capturing vehicle image data within the traffic control segment in real time includes the steps of:
S11, deploying binocular identification cameras on a road brake control road section, initializing binocular identification camera parameters and calibrating synchronously;
S12, capturing continuous video frames of the vehicles in the control road section in real time by using the calibrated binocular identification cameras and preprocessing the video frames;
And S13, generating a depth map based on the preprocessed video frame to obtain vehicle image data.
Specifically, binocular identification cameras are deployed on two sides of each lane of a road brake control road section, detailed parameter settings are carried out on the binocular cameras, including focal length, exposure time and frame rate, so as to adapt to different ambient light and traffic conditions, and calibration software or tools are utilized to synchronously calibrate the binocular cameras, wherein the calibration process comprises accurate adjustment of imaging positions, angles and focuses of the cameras, so that the binocular cameras can accurately capture stereoscopic images; capturing continuous video frames of vehicles in the control road section in real time by using the calibrated binocular identification cameras, and preprocessing the captured video frames, including denoising, contrast adjustment, color correction and the like, so as to improve the image quality; based on the preprocessed video frames, a depth map is generated by utilizing the binocular stereoscopic vision principle, the depth map can show the relative position and depth information of an object in space, and vehicle image data including the size, shape, position and motion trail of a vehicle are extracted from the depth map and serve as the basis for subsequent analysis of the behavior and traffic flow state of the vehicle.
In one embodiment, constructing a gate traffic analysis model, identifying vehicle image data, and analyzing the identification result by using a cluster tracking algorithm to obtain traffic flow state characteristics, comprising the following steps:
S21, constructing a gate traffic analysis model, and identifying vehicle characteristics in vehicle image data;
s22, completing classification and labeling of the vehicles according to the identification result;
s23, analyzing traffic flow state characteristics of the road brake control road section by using a cluster tracking algorithm based on the classification and labeling results.
In one embodiment, analyzing traffic flow status characteristics of a road segment using a cluster tracking algorithm based on classification and labeling results comprises the steps of:
s231, selecting an evaluation index based on the classification and labeling results, and normalizing the data of different evaluation indexes;
S232, simulating the movement of the road traffic control road section vehicles in the traffic network by using a cluster tracking algorithm;
S233, according to the simulation result, the traffic fluency of each lane is calculated respectively, and the traffic state characteristics of the road brake control section are obtained.
Specifically, the cluster tracking algorithm is a shoal of fish algorithm, and the behavior of the vehicle on the road brake control road section is simulated by simulating the shoal of fish behavior in the nature through the cluster tracking algorithm.
In one embodiment, simulating movement of a road-controlled road segment vehicle in a traffic network using a cluster tracking algorithm includes the steps of:
s2321, initializing a simulated vehicle position by using a cluster tracking algorithm and setting a movement rule;
S2322, simulating lane-changing and lane-splitting behaviors of the vehicle based on the split movement rule;
s2323, simulating the same-road converging behavior of the vehicle based on the converging movement rule.
Specifically, based on the data of the actual traffic flow, the position of the simulated vehicles is initialized, comprising determining the starting position of each vehicle in the traffic network as the position of fish in the shoal, and determining the basic behavior rules in the cluster tracking algorithm, and the movement of the simulated vehicles is guided by the basic logic (lane keeping, traffic signal adherence) of the simulated real vehicles.
Specifically, in the cluster tracking algorithm, the foraging behavior of the fish shoals is simulated by setting a diversion movement rule, the process of searching foods by the fish shoals in the diversion movement rule corresponds to the vehicle changing lanes according to the current traffic condition (such as front congestion) to search a more smooth path, the diversion movement rule comprises analyzing the traffic flow and the vehicle speed of the current road and predicting the future condition of each lane, and the vehicle is simulated to perform lane changing operation according to the road condition based on the diversion movement rule so as to realize more efficient traffic flow, thereby guiding the vehicle to perform optimal lane changing decision.
Specifically, in the cluster tracking algorithm, the crowd behavior of the shoal of fish is simulated by setting a converging movement rule, and the behavior of keeping the shoal of fish close to each other in the converging movement rule corresponds to keeping a proper safety distance in the same lane by vehicles, avoiding collision and keeping smooth traffic flow, and the behavior of the vehicles when keeping the lanes is simulated based on the converging movement rule, including adjusting the speed to adapt to the running speed of the preceding vehicles, so that safe converging operation is performed during lane merging.
In one embodiment, simulating lane-changing lane-splitting behavior of a vehicle based on a split movement rule includes the steps of:
s23221, analyzing the current traffic condition, and providing an optional path for the simulated vehicle;
s23222, evaluating the influence of lane change and diversion behaviors on traffic flow based on the selectable path, and determining a safe path;
s23223, executing lane change operation according to the safety path to complete the lane change and diversion behavior of the simulated vehicle;
Based on the confluence movement rule, the simulation of the same-lane confluence behavior of the vehicle comprises the following steps:
S23231, collecting driving data of vehicles in the same lane, and evaluating interaction among the vehicles;
s23232, analyzing how the vehicle responds to the behaviors of other vehicles, and setting a speed and a distance threshold value in the converging lane;
s23233, simulating vehicle running according to the set threshold value, and completing simulating the same-road converging behavior of the vehicle.
Specifically, the split movement rules include providing a possible smoother path selection for the simulated vehicle based on traffic conditions, which is similar to the process of finding food by fish in a shoal algorithm, performing lane changing operations in a simulated environment by predicting the traffic flow, the speed and the future conditions of the road, observing the behavior of the vehicle on a new lane, evaluating the influence of the lane changing operations on the traffic flow, the speed and the overall traffic smoothness, ensuring that the lane changing operations conform to traffic rules and safety requirements, determining a safe path from the provided selectable paths, improving the efficiency and safety of traffic flow, and finally realizing the lane changing operations by changing the path and speed of the simulated vehicle.
Specifically, the merging movement rule comprises the steps of adjusting the speed of the vehicle and keeping the safe distance between vehicles according to the speed of the front vehicle, and conducting guiding of safe merging, and the method is similar to the process of keeping the shoal of fish close to each other in a shoal algorithm, by predicting the interaction of the vehicles in the same lane, the speed of the vehicle is adjusted by simulating the vehicles according to the speed and the behavior of the front vehicle so as to keep smooth traffic flow, the speed and the distance threshold value of the vehicles in the merging lane are set, the driving of the vehicles is simulated according to the set threshold value, the simulated behavior is ensured to accord with the traffic safety rule, the safety and the efficiency of the merging process are improved, and finally the same-lane merging operation is realized by simulating the normal driving of the speed and the distance of the vehicles kept in the threshold value.
In one embodiment, according to the simulation result, calculating the traffic fluency of each lane, and obtaining the traffic flow state characteristics of the road brake control section includes the following steps:
S2331, calculating regional traffic fluency by using a granularity regional characteristic algorithm according to the simulation result of the lane change and diversion behavior of the vehicle;
S2332, calculating global traffic fluency by using a granularity global adaptation algorithm according to the simulation result of the same-lane converging behavior of the vehicle;
s2333, comparing the regional traffic fluency with the global traffic fluency, and updating the simulated vehicle position based on the comparison result;
S2334, repeating the steps S2331-S2333 until the preset iteration times are reached;
and S2335, collecting the final position of the simulated vehicle to obtain the traffic flow state characteristics of the road brake control road section.
Specifically, comparing the calculated regional traffic fluency with the global traffic fluency: if the regional traffic smoothness is higher, the lane change and diversion behavior is more effective, the position of the simulated vehicle is adjusted at the moment so as to simulate more lane change operations, so that traffic smoothness is promoted, if the global traffic smoothness is higher, the traffic flow which keeps smooth in the same lane is more effective, the lane change behavior is reduced at the moment, the confluence operation of the vehicle on the same lane is increased, and therefore, the position of the simulated vehicle is correspondingly adjusted based on a comparison result, so that the simulated vehicle is more approximate to an ideal traffic flow state; and then gradually optimizing the position of the simulated vehicle and the state of the whole traffic flow through continuous iteration: firstly, setting a preset iteration number to ensure that an optimal state can be converged in reasonable time, then, after the preset iteration number is reached, collecting the final position of a simulated vehicle, comprehensively obtaining traffic flow state characteristics of a road brake control road section according to the final vehicle position and a behavior mode, including flow, flow velocity and congestion conditions, and finally, effectively simulating and analyzing the characteristics of traffic flow through combination of an area and overall fluency assessment, and ensuring efficient operation of an overall traffic system.
In one embodiment, according to the simulation result of the lane-changing and lane-dividing behavior of the vehicle, calculating the regional traffic smoothness by using the granularity regional characteristic algorithm comprises the following steps:
S23311, selecting a vehicle neighborhood direction and extracting a vehicle neighborhood direction vector characteristic according to a vehicle lane change and diversion behavior simulation result;
s23312, marking each vehicle neighborhood based on the extracted neighborhood direction vector features;
s23313, calculating a vehicle neighborhood mean value by using a granularity region characteristic algorithm according to each vehicle neighborhood to obtain region passing fluency.
Specifically, the granularity region feature algorithm is a small granularity algorithm, different neighborhood spaces are formed by extracting directional feature vectors with small granularity, and then the average value of the multi-size neighborhood is calculated.
Specifically, a calculation formula for calculating a vehicle neighborhood mean value by using a granularity region feature algorithm is as follows:
Wherein LY l (a, b) represents the vehicle neighborhood mean;
a-l and a+l respectively represent the minimum value and the maximum value of the coordinates of the vehicle in the horizontal reference direction;
b-l and b+l respectively represent the minimum value and the maximum value of the coordinates of the vehicle in the vertical reference direction;
m and n respectively represent a horizontal reference direction coordinate and a vertical reference direction coordinate of the current vehicle neighborhood position;
f (m, n) represents a vehicle neighborhood vector value;
(2l+1) 2 denotes a vehicle domain size, where l denotes a coefficient determining a vehicle domain size, and l is not less than 1.
In one embodiment, calculating the global traffic smoothness by using the granularity global adaptation algorithm according to the simulation result of the vehicle on-road converging behavior comprises the following steps:
s23321, initializing a vehicle flow cluster according to the simulation result of the same-road confluence behavior of the vehicles, and evaluating the fitness of each vehicle;
S23322, calculating the speed and the position of the vehicles in the vehicle flow cluster by using a granularity global adaptation algorithm based on the evaluation result;
And S23323, updating the speed and the position of the vehicle according to the calculation result to obtain the global traffic fluency.
Specifically, a vehicle flow cluster is initialized according to a simulation result of the same-lane converging behavior of vehicles, the fitness of each vehicle is evaluated, the vehicle speed and the safe vehicle distance of the vehicles keep stable have higher fitness, the speed data of the vehicles on the same lane are calculated according to the current state and the surrounding environment of the vehicles by using a granularity global adaptation algorithm, the consistency and the fluctuation condition of the speeds are inspected, the relative positions among the vehicles are calculated, the uniformity and the safety of the vehicle distance are evaluated, the calculation result is counted, how the vehicles respond to the speed change of the vehicles in front and how the vehicles adjust the speed of the vehicles while keeping the safe distance are analyzed, and the smoothness of traffic flow is quantified by using the statistical analysis of the data to obtain global traffic smoothness.
Specifically, the particle size global adaptation algorithm is a particle swarm optimization algorithm, and a formula for calculating the vehicle position in the vehicle flow cluster by using the particle size global adaptation algorithm is as follows:
the formula for calculating the vehicle speed in the vehicle flow cluster by using the granularity global adaptation algorithm is as follows:
In the method, in the process of the invention, Representing the position of the xth vehicle in the y dimension of the kth generation;
representing the speed of the xth vehicle in the kth dimension;
g k denotes inertial weight;
U c and U d represent learning factors;
And (3) with Representing two random numbers;
And (3) with The position of the xth vehicle in the y dimension of the kth generation of optimal solution and the global optimal solution is represented respectively.
As shown in fig. 2, according to another embodiment of the present invention, there is also provided a 5G intelligent road management system based on binocular identification, the 5G intelligent road management system based on binocular identification including:
The deployment acquisition module 1 is used for deploying binocular identification cameras on a road brake control road section and capturing vehicle image data in the road brake control road section in real time;
the recognition analysis module 2 is used for constructing a gate traffic analysis model, recognizing vehicle image data, and analyzing the recognition result by utilizing a cluster tracking algorithm to obtain traffic flow state characteristics;
the mode judging module 3 is used for judging the current road gate traffic mode according to the traffic flow state characteristics;
the communication management module 4 is used for sending the judging result to the intelligent road brake management platform by utilizing the 5G communication network and remotely controlling the road brake release vehicle based on the current road brake traffic mode;
The deployment acquisition module 1 is connected with the mode judgment module 3 through the recognition analysis module 2, and the mode judgment module 3 is connected with the communication management module 4.
In order to facilitate understanding of the above technical solutions of the present invention, the following describes in detail the working principle or operation manner of the present invention in the actual process.
In practical application, taking a road toll gate with six lanes as an example, firstly, each lane is provided with a binocular identification camera, vehicle image data of each lane is continuously monitored by the binocular identification camera, then the vehicle image data is identified by constructing a gate traffic analysis model, the identification result is analyzed by using a cluster tracking algorithm to obtain traffic flow state characteristics, and then the current gate traffic mode is judged by using the gate traffic analysis model according to the traffic flow state characteristics: under the normal mode, the road toll gate only opens the middle double lane and the right double lane; when the traffic flow entering the road gate of the highway toll station is detected to be rapidly increased through analyzing the identification result in the early rush hour period, the mode of the rush hour period needs to be entered is intelligently judged, then the judgment result is sent to an intelligent road gate management platform by utilizing a 5G communication network, the remote management platform opens a left side double lane through instructions, the lane opening frequency in the direction of entering a city is increased, and meanwhile, the traffic pressure is effectively relieved when the traffic signal of the adjacent intersection is optimized; when the traffic flow entering the road toll gate of the road toll station is detected to be about to be reduced by analyzing the identification result in the low-peak period at night, the road gate system is automatically switched to a low-flow mode, the left side double lanes and the middle double lanes are closed, and only the right side double lanes are opened, so that unnecessary road gate operation is reduced, and energy sources are saved and the influence on the environment is reduced; in addition, the invention can also deal with emergency, and when traffic accidents or road maintenance occur on the road brake control road section, the road brake mode and signal lamp timing can be quickly adjusted, the vehicle is guided to select an alternative route, and the traffic jam and delay are effectively reduced.
In summary, by means of the technical scheme, the traffic efficiency and the mobility can be improved, the vehicle information can be captured in real time through a high-precision binocular recognition technology, the traffic flow state characteristics are accurately analyzed by combining a cluster tracking algorithm, accurate data support is provided for traffic management, the traffic flow state is intelligently judged, the opening and closing of the road gate is adjusted according to the real-time traffic condition, vehicles are guided to reasonably split and merge, the traffic pressure can be effectively relieved by increasing the traffic capacity of a specific road gate lane or adjusting signal lamps in the traffic peak period, the congestion is reduced, the unnecessary road gate operation can be reduced in the period with lower traffic flow, the energy consumption is reduced, the energy saving effect is realized, the traffic capacity and the mobility of roads are greatly improved through the dynamic adjustment mechanism, the vehicle queuing waiting time is reduced, and the overall traffic efficiency is improved; meanwhile, the traffic safety and accident coping capability can be enhanced, the invention not only can monitor traffic flow state in real time, but also can predict potential traffic risk through simulation analysis, and timely make coping measures, thereby remarkably improving traffic safety, and by utilizing the high-speed and low-delay characteristics of the 5G network, the invention can receive and process a large amount of traffic data in real time, rapidly respond to various emergency situations, ensure the efficiency and timeliness of accident handling and vehicle evacuation, greatly improve the safety performance of roads and ensure the life and property safety of drivers and passengers through an intelligent accident pre-warning and emergency handling mechanism; in addition, the implementation of the invention not only optimizes the traffic management of a single road section, but also provides powerful technical support for intelligent upgrading of the whole urban traffic system, and all traffic nodes and facilities can exchange information in real time, cooperate to realize omnibearing traffic monitoring, management and service by integrating high-precision vehicle identification technology, advanced traffic flow analysis algorithm and quick 5G communication network, thereby laying a solid foundation for constructing the intelligent traffic system, realizing data sharing and linkage control with an urban traffic command center, coping with complex and changeable traffic conditions together, improving the intelligent level of traffic management, facilitating collection and analysis of a large amount of traffic data, providing scientific basis for urban traffic planning and policy formulation, and promoting long-term optimization and sustainable development of the traffic system.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The 5G intelligent road management method based on binocular identification is characterized by comprising the following steps of:
S1, deploying binocular identification cameras on a road brake control road section, and capturing vehicle image data in the road brake control road section in real time;
S2, constructing a gate traffic analysis model, identifying vehicle image data, and analyzing an identification result by using a cluster tracking algorithm to obtain traffic flow state characteristics;
s3, judging the current road gate traffic mode according to the traffic flow state characteristics;
S4, sending a judging result to an intelligent gateway management platform by using a 5G communication network, and remotely controlling a gateway release vehicle based on a current gateway traffic mode;
The method for constructing the gate traffic analysis model, identifying vehicle image data, analyzing the identification result by utilizing a cluster tracking algorithm, and obtaining traffic flow state characteristics comprises the following steps:
S21, constructing a gate traffic analysis model, and identifying vehicle characteristics in vehicle image data;
s22, completing classification and labeling of the vehicles according to the identification result;
s23, analyzing traffic flow state characteristics of the road brake control road section by using a cluster tracking algorithm based on classification and labeling results;
the method for analyzing the traffic flow state characteristics of the road brake control road section by using the cluster tracking algorithm based on the classification and labeling results comprises the following steps:
s231, selecting an evaluation index based on the classification and labeling results, and normalizing the data of different evaluation indexes;
S232, simulating the movement of the road traffic control road section vehicles in the traffic network by using a cluster tracking algorithm;
s233, respectively calculating the traffic fluency of each lane according to the simulation result to obtain the traffic state characteristics of the road brake control section;
The method for simulating the movement of the road-controlled road section vehicle in the traffic network by using the cluster tracking algorithm comprises the following steps of:
s2321, initializing a simulated vehicle position by using a cluster tracking algorithm and setting a movement rule;
S2322, simulating lane-changing and lane-splitting behaviors of the vehicle based on the split movement rule;
S2323, simulating the same-channel converging behavior of the vehicle based on the converging movement rule;
Based on the split movement rule, the simulation of the lane change and split behavior of the vehicle comprises the following steps:
s23221, analyzing the current traffic condition, and providing an optional path for the simulated vehicle;
s23222, evaluating the influence of lane change and diversion behaviors on traffic flow based on the selectable path, and determining a safe path;
s23223, executing lane change operation according to the safety path to complete the lane change and diversion behavior of the simulated vehicle;
Based on the confluence movement rule, the simulation of the same-lane confluence behavior of the vehicle comprises the following steps:
S23231, collecting driving data of vehicles in the same lane, and evaluating interaction among the vehicles;
s23232, analyzing how the vehicle responds to the behaviors of other vehicles, and setting a speed and a distance threshold value in the converging lane;
s23233, simulating vehicle running according to the set threshold value, and completing simulating the same-road converging behavior of the vehicle.
2. A5G intelligent road management method based on binocular identification according to claim 1, wherein, the method for capturing the vehicle image data in the road control section in real time comprises the following steps of:
S11, deploying binocular identification cameras on a road brake control road section, initializing binocular identification camera parameters and calibrating synchronously;
S12, capturing continuous video frames of the vehicles in the control road section in real time by using the calibrated binocular identification cameras and preprocessing the video frames;
And S13, generating a depth map based on the preprocessed video frame to obtain vehicle image data.
3. The 5G intelligent road traffic management method based on binocular recognition according to claim 1, wherein the calculating the traffic fluency of each lane according to the simulation result, obtaining the traffic flow status characteristics of the road traffic control section comprises the following steps:
S2331, calculating regional traffic fluency by using a granularity regional characteristic algorithm according to the simulation result of the lane change and diversion behavior of the vehicle;
S2332, calculating global traffic fluency by using a granularity global adaptation algorithm according to the simulation result of the same-lane converging behavior of the vehicle;
s2333, comparing the regional traffic fluency with the global traffic fluency, and updating the simulated vehicle position based on the comparison result;
S2334, repeating the steps S2331-S2333 until the preset iteration times are reached;
and S2335, collecting the final position of the simulated vehicle to obtain the traffic flow state characteristics of the road brake control road section.
4. The 5G intelligent road traffic management method based on binocular recognition according to claim 3, wherein the calculating the regional traffic smoothness by using the granularity regional characteristic algorithm according to the vehicle lane change and diversion behavior simulation result comprises the following steps:
S23311, selecting a vehicle neighborhood direction and extracting a vehicle neighborhood direction vector characteristic according to a vehicle lane change and diversion behavior simulation result;
s23312, marking each vehicle neighborhood based on the extracted neighborhood direction vector features;
s23313, calculating a vehicle neighborhood mean value by using a granularity region characteristic algorithm according to each vehicle neighborhood to obtain region passing fluency.
5. The 5G intelligent traffic management method based on binocular recognition according to claim 4, wherein the calculating the global traffic fluency by using the granularity global adaptation algorithm according to the simulation result of the same-lane converging behavior of the vehicles comprises the following steps:
s23321, initializing a vehicle flow cluster according to the simulation result of the same-road confluence behavior of the vehicles, and evaluating the fitness of each vehicle;
S23322, calculating the speed and the position of the vehicles in the vehicle flow cluster by using a granularity global adaptation algorithm based on the evaluation result;
And S23323, updating the speed and the position of the vehicle according to the calculation result to obtain the global traffic fluency.
6. A binocular recognition-based 5G intelligent road management system for implementing the binocular recognition-based 5G intelligent road management method of any one of claims 1 to 5, wherein the binocular recognition-based 5G intelligent road management system comprises:
The deployment acquisition module is used for deploying binocular identification cameras on the road brake control road section and capturing vehicle image data in the road brake control road section in real time;
the recognition analysis module is used for constructing a gate traffic analysis model, recognizing vehicle image data, and analyzing the recognition result by utilizing a cluster tracking algorithm to obtain traffic flow state characteristics;
The mode judging module is used for judging the current road gate traffic mode according to the traffic flow state characteristics;
The communication management module is used for sending the judging result to the intelligent barrier management platform by utilizing the 5G communication network and remotely controlling the barrier release vehicle based on the current barrier traffic mode;
The deployment acquisition module is connected with the mode judgment module through the identification analysis module, and the mode judgment module is connected with the communication management module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410679084.XA CN118262302B (en) | 2024-05-29 | 2024-05-29 | Binocular identification-based 5G intelligent road management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410679084.XA CN118262302B (en) | 2024-05-29 | 2024-05-29 | Binocular identification-based 5G intelligent road management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118262302A CN118262302A (en) | 2024-06-28 |
| CN118262302B true CN118262302B (en) | 2024-09-17 |
Family
ID=91613175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410679084.XA Active CN118262302B (en) | 2024-05-29 | 2024-05-29 | Binocular identification-based 5G intelligent road management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118262302B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117392844A (en) * | 2023-10-27 | 2024-01-12 | 浪潮智慧科技有限公司 | Road traffic safety monitoring method, equipment and medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361646B (en) * | 2014-11-28 | 2016-08-17 | 大连海事大学 | A kind of highway quickly passes in and out Fare Collection System and method of work thereof |
| CN106600727A (en) * | 2016-12-20 | 2017-04-26 | 北京安杰新时代信息科技有限公司 | Novel and rapid highway toll system and device |
| CN110610608A (en) * | 2019-08-20 | 2019-12-24 | 江苏金晓电子信息股份有限公司 | Traffic state identification method based on binocular camera |
| DE102020211698A1 (en) * | 2020-09-18 | 2022-03-24 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method for controlling a traffic flow |
| CN117319609A (en) * | 2023-10-27 | 2023-12-29 | 黑龙江睿软科技有限公司 | Internet of things big data intelligent video monitoring system and method |
| CN117392853B (en) * | 2023-12-11 | 2024-04-12 | 山东通维信息工程有限公司 | Big data intelligent lane control system based on high in clouds |
-
2024
- 2024-05-29 CN CN202410679084.XA patent/CN118262302B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117392844A (en) * | 2023-10-27 | 2024-01-12 | 浪潮智慧科技有限公司 | Road traffic safety monitoring method, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118262302A (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11069233B1 (en) | Video-based main road cooperative signal machine control method | |
| CN109147331B (en) | Road congestion state detection method based on computer vision | |
| JP6570731B2 (en) | Method and system for calculating passenger congestion | |
| CN111540201B (en) | Vehicle queuing length real-time estimation method and system based on roadside laser radar | |
| CN108983219A (en) | A kind of image information of traffic scene and the fusion method and system of radar information | |
| CN109152185A (en) | A kind of multi-source perception intelligent street lamp control system | |
| EP3631616A1 (en) | Road traffic control system, method, and electronic device | |
| US10699568B1 (en) | Video-based crossroad signal machine control method | |
| CN109584567A (en) | Traffic management method based on bus or train route collaboration | |
| CN111696348A (en) | Multifunctional intelligent signal control system and method | |
| CN115206115A (en) | Road network congestion area control method based on multi-source data edge calculation in intelligent networking environment | |
| CN111951576A (en) | Traffic light control system based on vehicle identification and method thereof | |
| CN118366310B (en) | Road construction warning management system based on cloud computing | |
| CN118262302B (en) | Binocular identification-based 5G intelligent road management method and system | |
| CN111754790B (en) | Ramp entrance traffic control system and method based on radar | |
| KR20180068462A (en) | Traffic Light Control System and Method | |
| CN113689703B (en) | Vehicle shunting control method and device, electronic equipment and storage medium | |
| CN107730890B (en) | Intelligent transportation method based on traffic flow speed prediction in real-time scene | |
| CN112489423B (en) | Vision-based urban road traffic police command method | |
| CN110164153A (en) | A kind of adaptive timing method of traffic signals | |
| CN113053100A (en) | Method and device for estimating bus arrival time | |
| CN109584569A (en) | Traffic control system based on roadside fixed test equipment | |
| Al-Ani et al. | Intelligent traffic light control system based image intensity measurment | |
| Mittal et al. | Macroscopic traffic flow model based dynamic road traffic lights management framework | |
| CN109584570A (en) | Traffic management method based on roadside fixed test equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |